Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Blazingly Fast LoRA powered by @FAL and Hugging Face Providers! 🔥 Bring any compatible LoRA and get generations at lightning fast speeds! ⚡ Lots more to come soon!

Vaibhav (VB) Srivastav

41,592 subscribers

27,212 views • 1 year ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Vaibhav (VB) Srivastav1 year ago

Play with it here, credits to @multimodalart for building the OG LoRA Explorer!

OPEN1 year ago

Introducing OPEN, the first genre-defining AAA metaverse gaming experience with top-tier IP powered by web3 technology. Coming to @thereadyverse. #opensoon

1M views1 year ago

@FAL @reach_vb Putting custom LoRA not working in the space

Vaibhav (VB) Srivastav1 year ago

@FAL Which LoRA was it?

Bail0ut1 year ago

@FAL Wen self improving llm?

Vaibhav (VB) Srivastav1 year ago

@FAL thinking

Sam Woods1 year ago

@FAL Faster LoRA is always a win!

Vaibhav (VB) Srivastav1 year ago

@FAL Yes sir

Petr Glaser1 year ago

@FAL Can we also easily create custom LoRA on HF? 🤔

Vaibhav (VB) Srivastav1 year ago

@FAL Yeah! Quite a few trainers out there - will whip up a script

Silvio S.1 year ago

@FAL @blovereviews

Related Videos

Fast. Seamless. Smart! 🔥 The time has come to experience Lightning-fast transactions only with Reef Swap!⚡ More details will be out soon. 👀 #ReefSwap

Fast. Seamless. Smart! 🔥 The time has come to experience Lightning-fast transactions only with Reef Swap!⚡ More details will be out soon. 👀 #ReefSwap

ReefSwap | DEX

35,122 views • 3 years ago

Experience Airtel 5G Smart Connect Unlimited data. Lightning fast speeds. Endless streaming, gaming, and working without limits. Get yours at any Airtel store today with FREE installation within 48 hours.

Experience Airtel 5G Smart Connect Unlimited data. Lightning fast speeds. Endless streaming, gaming, and working without limits. Get yours at any Airtel store today with FREE installation within 48 hours.

Airtel Nigeria

520,204 views • 9 months ago

Introducing Kintsu Zap ⚡ Zap any asset From any chain Straight into sHYPE The fastest way to get to Hyperliquid Powered by @MayanFinance and Wormhole

Introducing Kintsu Zap ⚡ Zap any asset From any chain Straight into sHYPE The fastest way to get to Hyperliquid Powered by @MayanFinance and Wormhole

Kintsu

14,353 views • 9 months ago

⚡️ Ideogram V4 Fast and Instant are now available on fal -The fastest Ideogram V4 variants, built in-house by fal -Full images in 0.4 seconds on Instant and one second on Fast -Same prompts and parameters as the original at up to 8x the speed

⚡️ Ideogram V4 Fast and Instant are now available on fal -The fastest Ideogram V4 variants, built in-house by fal -Full images in 0.4 seconds on Instant and one second on Fast -Same prompts and parameters as the original at up to 8x the speed

fal

35,384 views • 20 days ago

We’re revolutionising your broadband connection and your…breakfast! We’ve been busy rolling out Full Fibre Broadband (and cereal) to thousands of homes across Ireland, with lightning-fast speeds of up to 2 Gig and 99.9% reliability, get ready for a connection like no other. ⚡

We’re revolutionising your broadband connection and your…breakfast! We’ve been busy rolling out Full Fibre Broadband (and cereal) to thousands of homes across Ireland, with lightning-fast speeds of up to 2 Gig and 99.9% reliability, get ready for a connection like no other. ⚡

Virgin Media Ireland

28,812 views • 3 years ago

🇮🇷 Iran’s Fattah hypersonic missile is powered by its own engine and can blaze through the skies at speeds up to Mach 15. It’s not just fast — it’s a game-changer.

🇮🇷 Iran’s Fattah hypersonic missile is powered by its own engine and can blaze through the skies at speeds up to Mach 15. It’s not just fast — it’s a game-changer.

Defense Intelligence

16,006 views • 1 year ago

Hey Rookie… you think you can score on me? ⚡ 🏟️ Climb the arenas, Beat the bosses, Earn your rank! 💥 Rise to the top of the league and you’ll get written in the sky. Powered by Sei 🔴 for ⚡ lightning-fast matches, bringing glory on-chain.

Hey Rookie… you think you can score on me? ⚡ 🏟️ Climb the arenas, Beat the bosses, Earn your rank! 💥 Rise to the top of the league and you’ll get written in the sky. Powered by Sei 🔴 for ⚡ lightning-fast matches, bringing glory on-chain.

Sei Baller

14,876 views • 8 months ago

Introducing 𝗦𝘂𝗿𝗳: your shortcut to crypto insights 🌊 Now in private, invite-only beta, Surf is a blazing-fast Mac app powered by Instantly search any project, spot trends, and get alpha without juggling tabs. 𝗝𝘂𝘀𝘁 𝗵𝗶𝘁 ⌘ + 𝗝

Introducing 𝗦𝘂𝗿𝗳: your shortcut to crypto insights 🌊 Now in private, invite-only beta, Surf is a blazing-fast Mac app powered by Instantly search any project, spot trends, and get alpha without juggling tabs. 𝗝𝘂𝘀𝘁 𝗵𝗶𝘁 ⌘ + 𝗝

Cyber

38,745 views • 1 year ago

Introducing Swap Powered by deBridge, you can now swap and bridge any supported asset, across chains. Seamlessly, inside Dexari. ⚡ Fast execution 🔗 Cross-chain compatibility 🛡️ 100% self-custodial Everything you need to move your capital, now built directly into the app.

Introducing Swap Powered by deBridge, you can now swap and bridge any supported asset, across chains. Seamlessly, inside Dexari. ⚡ Fast execution 🔗 Cross-chain compatibility 🛡️ 100% self-custodial Everything you need to move your capital, now built directly into the app.

Dexari

12,532 views • 9 months ago

⚡ Lightning-fast BTC swaps are now live on Exolix! We’re excited to introduce Bitcoin Lightning support via the Breez ⚡ SDK and Spark implementation, enabling ultra-fast, low-fee BTC swaps – fully non-custodial. Watch the demo to see how easy it is, and try it yourself 👇 🔗 Read more about how it works:

⚡ Lightning-fast BTC swaps are now live on Exolix! We’re excited to introduce Bitcoin Lightning support via the Breez ⚡ SDK and Spark implementation, enabling ultra-fast, low-fee BTC swaps – fully non-custodial. Watch the demo to see how easy it is, and try it yourself 👇 🔗 Read more about how it works:

Exolix

19,564 views • 5 months ago

40x faster than cursor and completely free We're teaming up with Cline to bring lightning-fast inference directly into your dev flow. Just watch the demo at 0:12s.... Get started today at

40x faster than cursor and completely free We're teaming up with Cline to bring lightning-fast inference directly into your dev flow. Just watch the demo at 0:12s.... Get started today at

Sarah Fong

280,693 views • 1 year ago

ACE-Step-1.5-xl is out now. We scaled the DiT decoder to 4B. And it shows better audio quality, better prompt following, and better musicality. It still fast -- 8 steps with turbo distillation. What didn't change: - Same generation API, same LoRA training code, same everything - All LM models (0.6B / 1.7B / 4B) fully compatible with all 3 variants - Your existing projects work with XL — no changes needed Try it for free at Weithgts and code: GitHub: Hugging Face: (3 variants: xl-base, xl-sft, xl-turbo) XL demos:

ACE-Step-1.5-xl is out now. We scaled the DiT decoder to 4B. And it shows better audio quality, better prompt following, and better musicality. It still fast -- 8 steps with turbo distillation. What didn't change: - Same generation API, same LoRA training code, same everything - All LM models (0.6B / 1.7B / 4B) fully compatible with all 3 variants - Your existing projects work with XL — no changes needed Try it for free at Weithgts and code: GitHub: Hugging Face: (3 variants: xl-base, xl-sft, xl-turbo) XL demos:

ACE Music

35,729 views • 3 months ago

It's out, and it comes with a demo🔥 Introducing Flux.2 [klein] Move ✨ > specialized move & resize LoRA for Flux.2 [klein] 9B > draw boxes manually or pick from auto-detected objects > works with fast 4-8 step inference 💨

It's out, and it comes with a demo🔥 Introducing Flux.2 [klein] Move ✨ > specialized move & resize LoRA for Flux.2 [klein] 9B > draw boxes manually or pick from auto-detected objects > works with fast 4-8 step inference 💨

Linoy Tsaban

59,059 views • 3 months ago

Check out mistral.rs, our #Rust-based open source inference engine allowing for fast #LLM serving for a variety of architectures including X-LoRA mixture-of-expert (MoE) models, Llama-3, Mistral/Mixtral, Gemma & many others. Built on the Hugging Face #Candle framework for #Rust w/ custom CUDA kernels in the backend (as well as support for Metal, Apple Accelerate, and Intel MKL for CPU use), you can easily create a REST API OpenAI compatible server or run via Python bindings. Key features include: ✅Prefix caching, continuous batching ✅Flash Attention V2 ✅Device offloading ✅GGUF or Hugging Face models ✅2, 3, 4, 5, 6 and 8 bit quantization ✅X-LoRA MoE non-granular scalings for fast inference ✅Grammar support ✅Continuous batching ✅LoRA support with weight merging ✅LlamaIndex 🦙 integration ...and much more. Incorporation into our GraphReasoning multi-agent modeling framework & LlamaIndex 🦙 allows you to combine in-context learning with adversarial agentic strategies, to dive deep into complex scientific analyses, such as to predict material behaviors, generate hypotheses, analyze papers and data, develop new research concepts, and much more. Check out mistral.rs: Join our Discord here: Rust Trending Rust Language

Check out mistral.rs, our #Rust-based open source inference engine allowing for fast #LLM serving for a variety of architectures including X-LoRA mixture-of-expert (MoE) models, Llama-3, Mistral/Mixtral, Gemma & many others. Built on the Hugging Face #Candle framework for #Rust w/ custom CUDA kernels in the backend (as well as support for Metal, Apple Accelerate, and Intel MKL for CPU use), you can easily create a REST API OpenAI compatible server or run via Python bindings. Key features include: ✅Prefix caching, continuous batching ✅Flash Attention V2 ✅Device offloading ✅GGUF or Hugging Face models ✅2, 3, 4, 5, 6 and 8 bit quantization ✅X-LoRA MoE non-granular scalings for fast inference ✅Grammar support ✅Continuous batching ✅LoRA support with weight merging ✅LlamaIndex 🦙 integration ...and much more. Incorporation into our GraphReasoning multi-agent modeling framework & LlamaIndex 🦙 allows you to combine in-context learning with adversarial agentic strategies, to dive deep into complex scientific analyses, such as to predict material behaviors, generate hypotheses, analyze papers and data, develop new research concepts, and much more. Check out mistral.rs: Join our Discord here: Rust Trending Rust Language

Markus J. Buehler

73,581 views • 2 years ago

We’ve integrated DLN – High Performance Cross-Chain Trading bridging widget to our Solana tab! Experience native cross-chain trading with deep liquidity and lightning-fast execution, powered by deBridge and Jupiter. Bridge a variety of tokens between 8 EVM chains and Solana at

We’ve integrated DLN – High Performance Cross-Chain Trading bridging widget to our Solana tab! Experience native cross-chain trading with deep liquidity and lightning-fast execution, powered by deBridge and Jupiter. Bridge a variety of tokens between 8 EVM chains and Solana at

Jupiter

182,555 views • 2 years ago

Introducing Grok Intelligence Beta 😂 A lightning-fast AI agent powered by the Grok Voice API! - Always-on & ready - Controls your entire computer (any task) - Blazing fast execution - Spins up & orchestrates multiple background agents - Checks email, sends messages - Creates images & videos instantly with Grok Imagine Built 100% native in Swift. This prototype is actually working. Should I keep building it and open source the whole thing?

Introducing Grok Intelligence Beta 😂 A lightning-fast AI agent powered by the Grok Voice API! - Always-on & ready - Controls your entire computer (any task) - Blazing fast execution - Spins up & orchestrates multiple background agents - Checks email, sends messages - Creates images & videos instantly with Grok Imagine Built 100% native in Swift. This prototype is actually working. Should I keep building it and open source the whole thing?

Dan

14,694 views • 1 month ago

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Xenova

103,001 views • 5 months ago